| Description |
1 online resource (424 pages) |
| Contents |
Cover; Title Page; Table of Contents; NEUROSCIENCE; Sigma-pi properties of spiking neurons; Towards a computational theory of rat navigation; Evaluating connectionist models in psychology and neuroscience; VISION; Self-organizing feature maps with lateral connections: Modeling ocular dominance; Joint solution of low, intermediate, and high level vision tasks by global optimization: Application to computer vision at low SNR; Learning global spatial structures from local associations; COGNITIVE MODELING; A connectionist model of auditory Morse code perception |
|
A competitive neural network model for the process of recurrent choiceA neural network simulation of numerical verbal-to-arabic transcoding; Combining models of single-digit arithmetic and magnitude comparison; Neural network models as tools for understanding high-level cognition: Developing paradigms for cognitive interpretation of neural network models; LANGUAGE; Modeling language as sensorimotor coordination; Structure and content in word production: Why it's hard to say dlorm; Investigating phonological representations: A modeling agenda |
|
Part-of-speech tagging using a variable context Markov modelQuantitative predictions from a constraint-based theory of syntactic ambiguity resolution; Optimality semantics; SYMBOLIC COMPUTATION AND RULES; What's in a rule? The past tense by some other name might be called a connectionist net; On the proper treatment of symbolism-A lesson from linguistics; Structure sensitivity in connectionist models; Looking for structured representations in recurrent networks; Back propagation with understandable results; Understanding neural networks via rule extraction and pruning |
|
Rule learning and extraction with self-organizing neural networksRECURRENT NETWORKS AND TEMPORAL PATTERN PROCESSING; Recurrent networks: State machines or iterated function systems?; On the treatment of time in recurrent neural networks; Finding metrical structure in time; Representations of tonal music: A case study in the development of temporal relationships; Applications of radial basis function fitting to the analysis of dynamical systems; Event prediction: Faster learning in a layered Hebbian network with memory; CONTROL; Issues in using function approximation for reinforcement learning |
|
Approximating Q-values with basis function representationsEfficient learning of multiple degree-of-freedom control problems with quasi-independent Q-agents; Neural adaptive control of systems with drifting parameters; LEARNING ALGORITHMS AND ARCHITECTURES; Temporally local unsupervised learning: The Maxln algorithm for maximizing input information; Minimizing disagreement for self-supervised classification; Comparison of two unsupervised neural network models for redundancy reduction; Solving inverse problems using an EM approach to density estimation |
| Summary |
The result of the 1993 Connectionist Models Summer School, the papers in this volume exemplify the tremendous breadth and depth of research underway in the field of neural networks. Although the slant of the summer school has always leaned toward cognitive science and artificial intelligence, the diverse scientific backgrounds and research interests of accepted students and invited faculty reflect the broad spectrum of areas contributing to neural networks, including artificial intelligence, cognitive science, computer science, engineering, mathematics, neuroscience, and physics. Providing an |
| Notes |
Estimating a-posteriori probabilities using stochastic network models |
|
Print version record |
| Subject |
Neural networks -- Congresses
|
|
Connectionism -- Congresses
|
|
Artificial intelligence -- Congresses
|
|
Cognitive science -- Congresses
|
|
Artificial intelligence
|
|
Cognitive science
|
|
Connectionism
|
| Genre/Form |
Conference papers and proceedings
|
| Form |
Electronic book
|
| Author |
Smolensky, Paul
|
|
Touretzky, David S
|
|
Elman, Jeffrey L
|
|
Weigend, Andreas S
|
| ISBN |
9781317780533 |
|
1317780531 |
|
